Empirical Bayes for Dynamic Bayesian Networks Using Generalized Variational Inference
This work addresses uncertainty quantification in dynamic models for researchers in Bayesian statistics, but it appears incremental as it builds on existing Generalized Variational Inference techniques.
The paper tackles the problem of learning Dynamic Bayesian Networks by applying an Empirical Bayes approach with Generalized Variational Inference to quantify uncertainty in structure and parameters, resulting in a method that samples from a mixture of DAG structures and parameter posteriors.
In this work, we demonstrate the Empirical Bayes approach to learning a Dynamic Bayesian Network. By starting with several point estimates of structure and weights, we can use a data-driven prior to subsequently obtain a model to quantify uncertainty. This approach uses a recent development of Generalized Variational Inference, and indicates the potential of sampling the uncertainty of a mixture of DAG structures as well as a parameter posterior.